Named after the hundred-eyed watchman of Greek myth, Argus watches the education landscape: spotting new opportunities, pressure-testing the ventures we're building, and tracing every read back to the real-world signals behind it.
The evidence library: the raw signals the pipeline is watching across the education ecosystem. Every idea is built from these.
arXiv:2607.03207v1 Announce Type: new Abstract: Automatic speech recognition (ASR) has advanced remarkably for standard speech, yet speech affected by neurological conditions remains a challenge. We present S-DiverSe (Spanish Diverse Speech), a corpus of 3.2 hours of in-the-wild Spanish speech from 22 speakers with amyotrophic lateral sclerosis, Parkinson's disease, and stroke. The dataset contains 444 manually transcribed audio segments with metadata on speaker sex, disease type, and intelligibility. S-DiverSe is designed to support ASR evaluation and development for neurologically affected Spanish speech. We describe the dataset, analyze its composition, and report baseline ASR results alongside initial adaptation experiments. Our findings reveal that heuristic text post-processing is more robust than fine-tuning for out-of-domain neurological Spanish speech. This underscores the need for dedicated in-the-wild Spanish benchmarks.
arXiv:2607.03166v1 Announce Type: new Abstract: Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads supervision over mostly shared templates. We formalize this as the Resolution Mismatch Problem and propose KARMA, which enumerates schema-constrained paths over domain knowledge graphs and verbalizes them into slot-aligned contrastive candidates. Slot-Parallel Alignment (SPA) then applies a decoupled slot-level objective to route preference supervision to discriminative entity-slots, with slot-aware masked attention serving as an optional packed-evaluation implementation. Across biomedical, computer-science, and chemistry benchmarks, KARMA outperforms base LLM and same-data SFT baselines, and compares favorably with sequence and token-level preference methods.
arXiv:2607.03160v1 Announce Type: new Abstract: This study examines how prompt language and translation theory-driven prompt design influence the quality of Spanish-Chinese journalistic translations generated by GPT-5.2. A parallel corpus of four editorials from El Pais was translated under 48 experimental conditions (4 prompt types, 3 prompt languages, and 4 articles). Translation quality was assessed using BLEU and BERTScore-F1 for automated evaluation, alongside human evaluation based on the Multidimensional Quality Metrics (MQM) framework. Automated metrics identified the baseline prompt (BASE) as the best-performing condition, whereas human evaluation ranked the brief-oriented prompt (BRIEF) highest (MQM: 8.66 vs. 7.84), a reversal likely attributable to the single-reference constraint inherent in automated measures. Sub-error type analysis revealed that translation theory-driven prompts selectively reduced Awkward style errors, while Unidiomatic style errors persisted across cond
arXiv:2607.03154v1 Announce Type: new Abstract: Multi-domain knowledge graph completion (MKGC) aims to improve missing triple prediction in a target KG by transferring knowledge from other support KGs. Existing methods typically enforce consistency constraints on equivalent entities across KGs to transfer knowledge, which risks suppressing domain-specific contextual information of entities. This design can also compromise entity representation information from all KG domains, impeding performance improvements, especially in low-resource data scenarios. To address this, we pioneer a generation-based paradigm for MKGC and propose DMKGC, a conditional diffusion-guided knowledge transfer framework. Our key insight is to treat each KG as a partial view of the entity entire information, and generate informative domain-general entity embeddings through diffusion models conditioned on support KGs. Particularly, we first initialize domain-agnostic entity embeddings as prior entity embeddings, a
arXiv:2607.03093v1 Announce Type: new Abstract: Thinking has emerged as a critical capability for Large Language Models (LLMs) tackling complex tasks. However, its reactive nature, where reasoning is passively triggered only upon receiving a user response, inevitably introduces latency that compromises conversational fluidity. This stands in sharp contrast to human dialogue, where speakers proactively anticipate and plan future content during natural pauses to ensure seamless interaction. To bridge this gap, we propose Proactive Thinking, a framework that empowers models to pre-compute potential response elements during conversational downtime instead of waiting idly for the next input. We then introduce a training-free baseline that can think ahead by anticipating future states, balancing efficiency and quality through speculative continual thinking. To evaluate this approach in practice, we adapt three benchmarks of varying complexity into time-aware environments that simulate real-t
arXiv:2607.03049v1 Announce Type: new Abstract: Fast estimation of the size of the largest overlap between tables enables blocking and query-by-table retrieval in large table repositories. The first and the state-of-the-art estimator Armadillo improves efficiency by embedding each table independently and approximating overlap ratio via embedding similarity. However, accurate estimation in heterogeneous repositories remains limited by three challenges: (C1) overlap depends on row-column structure, i.e., each matched cell must preserve both its row and column membership under a joint alignment of the two tables, but existing encodings leave this structure to be inferred indirectly; (C2) independent encoding provides no explicit channel for inter-table alignment signals, biasing prediction toward global similarity; (C3) naive value encodings overfit to corpus-specific distributions, causing cross-domain degradation. Hence, we propose ALORE, a scalable and domain-robust overlap ratio estim
arXiv:2607.03003v1 Announce Type: new Abstract: Social media posts are a rich and valuable source of data for analyzing mental health states and users' well-being using automated analysis tools. In this work, we demonstrate how we used a range of Natural Language Processing (NLP) methods, including Long Short-Term Memory (LSTM), BERT-based models, and Large Language Models (LLMs), for self-state and well-being analysis and summarization during the CLPsych Shared Task 2026. Our approach achieved one of the top Consistency and Contradiction scores for the summarization task and also middle-level results for the other tasks. By testing and developing such mental health-state estimation systems, we contributed to improving mental health support systems. We make our code available https://github.com/psytechlab/CLPsych2026/.
arXiv:2607.02980v1 Announce Type: new Abstract: Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention. Chunk-wise sparse attention offers a promising alternative, but all existing methods fall short of full attention because of their inaccurate chunk selection. We propose Hierarchical Landmark Sparse (HiLS) Attention, a chunk-wise sparse attention mechanism that learns chunk selection end-to-end under the language-modeling (LM) loss. HiLS factorizes attention hierarchically: each query performs attention independently with each retrieved chunk to extract chunk-specific information, and the resulting outputs are fused according to chunk retrieval scores. By incorporating retrieval scores into the forward attention computation, HiLS optimizes them directly with the LM loss, enabling end-to-end retrieval learning and native sparse training. Experimental results show that HiLS-Attention ac
arXiv:2607.02966v1 Announce Type: new Abstract: Cross-lingual retrieval-augmented generation (RAG) is often deployed in an English-evidence regime, where users query in diverse languages but retrieved passages remain English. In this setting, generation can fail despite strong base models: English evidence induces language drift (English or code-switching outputs) and models use evidence unreliably when producing non-English answers. We attribute these failures to two post-training challenges: (i) errors are prefix-dependent, so fixed-trajectory supervision suffers from prefix mismatch; and (ii) sequence-level (partly discrete / judge-based) rewards yield noisy credit assignment and high-variance updates. We propose TR-RAG, a teacher-regularized RL recipe that couples reward optimization with on-policy distillation on student-visited prefixes. A compact student samples on-policy answers, while a stronger frozen teacher is queried only on those prefixes and provides a prefix-wise studen
arXiv:2607.02881v1 Announce Type: new Abstract: Long-horizon behavior prediction aims to infer a user's next action based on a lengthy historical sequence, playing a crucial role in artificial intelligence field. The rise of large language models (LLMs) offers a promising direction for sequential behavior prediction, yet LLMs struggle with latent behavioral pattern induction and model-intrinsic cognitive biases when tackling long-horizon behavior prediction. Prior memory management methods follow a context-compression paradigm that attempts to address this task by alleviating the historical sequence burden, yet fail to resolve the core challenges. In this paper, we advocate a paradigm shift that reframes the lengthy historical sequence from a burden into a valuable resource to be exploited, and accordingly propose PraMem, which conducts beforehand practice over the lengthy historical sequence to build an experiential memory, thereby serving as the assisted input for accurate long-horiz
arXiv:2607.02862v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) and Dialect Identification (DID) are crucial for Indian languages, many of which are low-resource and exhibit significant dialectal differences. Existing methods often optimize ASR or DID individually, resulting in performance trade-offs. In this work, we propose a multimodal framework that jointly improves ASR and DID. Our method employs a Bottleneck Encoder to extract dialectal features from Conformer-based speech representations and a RoBERTa encoder to process ASR-generated CTC embeddings. A gating mechanism merges these features, followed by an attention encoder to refine the representations. The learned embeddings are concatenated with Conformer outputs to enhance ASR features. Evaluated on eight Indian languages with thirty-three dialects, our method achieves an average DID accuracy of 81.63% and average CER and WER of 4.65% and 17.73%, respectively. These results highlight the effectiveness of ou
arXiv:2607.02802v1 Announce Type: new Abstract: As LLMs are increasingly deployed as autonomous adjudicators in semi-open textual game environments, robust rule adherence becomes critical when user intent conflicts with system rules. However, these models are trained to be helpful and compliant, leaving them vulnerable to a class of attacks we term \textit{Rhetorical Injection}, where adversarial users exploit narrative framing techniques such as pseudo-logical reasoning and authoritative coercion to bypass adjudication logic. We present CoC-Seduce, a multi-agent adversarial benchmark built on Tabletop Role-Playing Game (TRPG) mechanics, an ideal instantiation of semi-open environments where rules are explicit for adjudication, yet interaction remains entirely in natural language. Three frontier models, i.e., GPT-5.4, Claude Sonnet 4.6, Gemini 3.5 Flash, serve as adversarial generators producing 5,376 samples across 4 world settings and 16 skill categories. We then benchmark 20 target
arXiv:2607.02770v1 Announce Type: new Abstract: We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemma 4 model suite features dense and Mixture-of-Experts architectures, ranging from 2.3B to 31B parameters. Alongside improved vision and audio encoders for all model sizes, we propose a unified, encoder-free architecture for our 12B model, which ingests raw audio and image patches. Furthermore, we integrate a thinking mode, enabling Gemma models to generate reasoning traces prior to responding. We improve inference speed, memory, and compute efficiency, as well as long-context abilities through critical design choices. Gemma 4 establishes a leap in performance across STEM, multimodal, and long-context benchmarks, and rivals larger, frontier open models in human-rated tasks.
arXiv:2607.02763v1 Announce Type: new Abstract: Spoken Question Answering (SQA) remains largely focused on high-resource languages and carefully recorded speech, limiting the reach of speech-LLM methods in low-resource settings. This paper investigates whether text-to-speech (TTS) can provide task-specific training data for Luxembourgish SQA without requiring a large human-recorded QA corpus. Starting from existing text-based QA resources, we translate questions into Luxembourgish, synthesize spoken questions with multiple TTS systems, and pair them with textual answers. We train a parameter-efficient SLAM-style architecture that connects a frozen Whisper encoder to frozen multilingual LLM backends through a learned projector and LoRA adapters. We compare MMS-TTS, Qwen3-TTS, and OmniVoice variants, including single-source corpora of about 48k questions and a 4TTS multi-source mix of approximately 230k questions. Evaluation on LLAMA-LB-Test with two real Luxembourgish speaker conditions
arXiv:2607.02757v1 Announce Type: new Abstract: Audio-language models can be prompted for code-switched speech, but their decoding is not optimized for code-switching and often fails at language boundaries. We propose a practical reinforcement learning with verifiable rewards recipe for data-efficient adaptation of audio-language models to code-switched ASR using group relative policy optimization, combining an error rate reward with a script fidelity reward that penalizes wrong writing systems and a two-pass draft-and-refinement procedure. Using Qwen2-Audio as a reproducible testbed across 10 language pairs, training on only TTS code-switched speech, we show that RLVR with 10% of the data matches LoRA supervised fine-tuning trained on the full dataset, with the largest gains on typologically distant pairs. The error rate reward eliminates translation errors while the script fidelity reward separately reduces script contamination without degradation. These gains transfer zero-shot to a
arXiv:2607.02734v1 Announce Type: new Abstract: Rapid growth in social media has transformed global communication by enabling fast information exchange, but it has also accelerated the spread of misinformation. Fake news, manipulated content, and provocative narratives are increasingly linked to social unrest, political instability, and mob violence. Incidents in South Asia and elsewhere demonstrate how false information disseminated via platforms such as Facebook and WhatsApp can trigger real-world harm, often spreading faster than fact-checking efforts can respond. To address this challenge, this chapter presents a multilingual, multimodal Natural Language Processing (NLP) framework for early detection of misinformation and violence-prone dynamics. A fused dataset of 138,256 Bangla and English samples was created by combining multiple benchmark datasets. The framework integrates XLM-RoBERTa for multilingual text representation, CLIP for visual embedding, and a multi-head attention me
arXiv:2607.02668v1 Announce Type: new Abstract: Large language models are inconsistent: varying prompts or including unrelated information can lead to unexpected changes in model outputs. The generator-validator (G-V) gap is one manifestation of this phenomenon, where LLMs generate responses that they then deem as invalid if re-queried to validate them. In this work, we introduce a new formulation of G-V consistency that involves a principled correction for utterance frequency. Specifically, generators often assign low likelihood to valid strings simply because those strings are a priori unlikely, which makes naive notions of G-V consistency unworkable. We show that under a natural model of rational agents answering questions with multiple answers, consistency of the validator with a frequency-corrected generator score emerges naturally. Our method, \emph{\FCPAname} (\FCPA), is a training objective implementing frequency-corrected G-V consistency for real-world LLMs. Our experimental r
arXiv:2606.16337v3 Announce Type: replace-cross Abstract: Predictive modeling for clinical decision support requires not only strong predictive performance but also transparent decision logic. Although deep learning and tree-based ensemble methods can achieve high accuracy, their black-box nature remains a major obstacle to clinical deployment. This challenge is further compounded by common characteristics of medical data, including limited sample sizes, severe class imbalance, and feature evolution arising from changes in diagnostic criteria and clinical documentation. To address these issues, we propose Medical Heuristic Learning (MHL), an instantiation of the learning beyond gradients paradigm for clinical prediction from structured medical data. Instead of relying on neural network weight updates, MHL uses a large language model (LLM) driven workflow that integrates statistical probes, medical knowledge probes, rule synthesis, and code-level iterative refinement to optimize a deter
arXiv:2606.15198v2 Announce Type: replace-cross Abstract: City landscapes viewed through home windows influence quality of life, yet perceptions of actual window views at the urban scale remain understudied. This study presents an approach for large-scale mapping of perceptions using 12,334 window view images (WVIs) collected from actual residential properties listed on real estate platforms in Wuhan, China, representing a rarely explored form of urban view imagery that offers advantages over the rendered or simulated window views commonly examined in previous studies. Through a non-immersive virtual reality platform, we collected 27,477 pairwise comparisons across six perceptual dimensions (e.g. preference) from 304 participants based on 499 WVIs. A hybrid neural network model was trained to predict human perceptions of all crowdsourced WVIs and map their spatial distribution. Results reveal significant spatial autocorrelation with distinct hot and cold spots across the whole city. Fl
arXiv:2606.08281v2 Announce Type: replace-cross Abstract: Safe physical human-robot interaction (pHRI) is fundamentally a problem of interaction dynamics: the robot must track a commanded motion, yield under human forces, respect actuator and joint limits, and stay predictable under persistent contact. Classical impedance control shapes this through a virtual spring-damper, but a sustained force produces the bias $e_\infty=-K_d^{-1}F_h$, trading accuracy for safety. We propose a predictive framework that makes interaction dynamics explicit through a linear double-integrator backbone: an operational-space feedforward cancels gravity and Coriolis terms and normalizes the task inertia, leaving a configuration-independent state-transition matrix with robot dependence isolated in the input matrix. This converts nonlinear torque-controlled pHRI into a linear constrained-control problem, so offset-free tracking, actuator feasibility, sampled-data joint-limit safety, and passivity filtering fo
arXiv:2605.22774v3 Announce Type: replace-cross Abstract: Assessing cognitive load continuously and at low latency would help adaptive human-computer interaction, but it remains hard because labeled data are scarce and models generalize poorly across subjects. Recent ECG foundation models, pre-trained on millions of clinical diagnostic ECG recordings, yet they do not apply directly to wearable devices when the sensor configuration and the task both differ. We present CogAdapt, a framework that adapts a clinical ECG foundation model to wearable cognitive load assessment. CogAdapt has two parts. LeadBridge is a learnable adapter that maps 3-lead wearable signals to a 12-lead-compatible representation. ProFine is a progressive fine-tuning strategy that unfreezes encoder layers in stages while limiting representational drift in the pre-trained model. On two public datasets (CLARE and CL-Drive) under leave-one-subject-out cross-validation, CogAdapt reaches macro-F1 of 0.626 and 0.768, impro
arXiv:2604.25596v2 Announce Type: replace-cross Abstract: Formal models for concurrent and distributed systems describe machines; the people who operate them are either ignored or treated as external environment. Yet, key distributed systems -- notably grassroots platforms -- include people operating their personal machines (smartphones), and their faithful description must include the states of both people and machines and how they jointly effect system behaviour. Here, we propose volition-guarded multiagent atomic transactions -- executed atomically by machines and guarded by their people's volitions -- as a novel mathematical foundation for specifying systems consisting of people operating machines. Each agent's state consists of a volitional state and machine state; a transaction is enabled when the machine precondition holds and the guarding persons are willing. For example, befriending two people is guarded by both; unfriending, by either; voluntary swap of coins and bonds is gua
arXiv:2604.11730v4 Announce Type: replace-cross Abstract: Using behavioural science, health interventions focus on behaviour change by providing a framework to help patients acquire and maintain healthy habits that improve medical outcomes. In-person interventions are costly and difficult to scale, especially in resource-limited regions. Digital health interventions offer a cost-effective approach, potentially supporting independent living and self-management. Automating such interventions, especially through machine learning, has recently gained considerable attention. Ambivalence and hesitancy (A/H) play a primary role for individuals to delay, avoid, or abandon health interventions. A/H are subtle and conflicting emotions that place a person in a state between positive and negative evaluations of a behaviour, or between acceptance and refusal to engage in it. They manifest as affective inconsistency across modalities or within a modality, such as language, facial, vocal expressions,
arXiv:2603.02070v3 Announce Type: replace-cross Abstract: When automating plan generation for a real-world sequential decision problem, the goal is often not to replace the human planner, but to facilitate an iterative reasoning and elicitation process, where the human's role is to guide the AI planner according to their preferences and expertise. In this context, explanations that respond to users' questions are crucial to improve their understanding of potential solutions and increase their trust in the system. To enable natural interaction with such a system, we present a multi-agent Large Language Model (LLM) architecture that is agnostic to the explanation framework and enables user- and context-dependent interactive explanations. We also describe an instantiation of this framework for goal-conflict explanations, which we use to conduct a user study comparing the LLM-powered interaction with a baseline template-based explanation interface.
arXiv:2602.19107v3 Announce Type: replace-cross Abstract: Robotaxis are emerging as a promising form of urban mobility, but removing human drivers fundamentally reshapes passenger-vehicle interaction and raises new design challenges. To inform robotaxi design based on real-world experience, we conducted 18 semi-structured interviews and autoethnographic ride experiences to examine users' perceptions, experiences, and expectations for robotaxi design. We found that users valued benefits such as increased agency and consistent driving. However, they also encountered challenges such as limited flexibility, insufficient transparency, and emergency handling concerns. Notably, users perceived robotaxis not merely as a mode of transportation, but as autonomous, semi-private transitional spaces, which made users feel less socially intrusive to engage in personal activities. Safety perceptions were polarized: some felt anxiety about reduced control, while others viewed robotaxis as safer than h
arXiv:2512.10785v3 Announce Type: replace-cross Abstract: Generative AI offers new opportunities for individualized and adaptive learning, e.g., through large language model (LLM)-based feedback systems. While LLMs can produce factually correct feedback for relatively straightforward conceptual tasks, delivering high-quality feedback for tasks that require advanced domain expertise, such as physics problem solving, remains a substantial challenge. This study presents the design and implementation of an LLM-based feedback system for physics problem solving grounded in evidence-centered design and reports a first evaluation within the German Physics Olympiad. Participants rated the usefulness and correctness of the generated feedback for each implemented problem. The collected ratings indicate that the feedback was generally perceived as useful and highly correct. However, an in-depth analysis revealed that the feedback contained errors in 20% of cases; errors that often went unnoticed b
arXiv:2508.21010v3 Announce Type: replace-cross Abstract: Existing Causal-Why Video Question Answering (VideoQA) models often struggle with higher-order reasoning, relying on opaque, monolithic pipelines that entangle video understanding, causal inference, and answer generation. These black-box approaches offer limited interpretability and tend to depend on shallow heuristics. We propose a novel, modular paradigm that explicitly decouples causal reasoning from answer generation, introducing natural language causal chains as interpretable intermediate representations. Inspired by human cognitive models, these structured cause-effect sequences bridge low-level video content with high-level causal reasoning, enabling transparent and logically coherent inference. Our two-stage architecture comprises a Causal Chain Extractor (CCE) that generates causal chains from video-question pairs, and a Causal Chain-Driven Answerer (CCDA) that derives answers grounded in these chains. To address the la
arXiv:2508.16771v3 Announce Type: replace-cross Abstract: Code Language Models (CodeLLMs) learn token importance from data correlations, whereas human developers attend selectively to semantically salient code. We present EyeMulator, a model-agnostic method that injects human visual-attention priors into CodeLLM fine-tuning without architectural changes. EyeMulator distills eye-tracking data into semantic salience and gaze-transition priors, then uses them to reweight token-level training losses. Across six backbones, two data regimes, and three CodeXGLUE tasks, the reported configurations yield positive matched-metric deltas in all 36 model-task-setting cells. Effects are largest for structure-preserving completion and translation, while summarization shows smaller but positive METEOR deltas. Session-mode and component-ablation analyses further show that reading, writing, semantic, and transition-derived priors provide complementary signal. Human-attention artifacts are available at h
arXiv:2507.02950v3 Announce Type: replace-cross Abstract: Large language models (LLMs) may support counseling training, yet evidence from Japanese-language interactions and automated quality ratings remains limited. We examined 18 fixed Japanese-language counseling transcripts generated through artificial intelligence (AI)-to-AI interactions under three counselor conditions: GPT-minimal (GPT-4-turbo with a minimal role instruction), GPT-SMDP (GPT-4-turbo with the Structured Multi-step Dialogue Prompt [SMDP]), and Claude-SMDP (Claude-3-Opus with SMDP). Fifteen counseling experts rated transcripts on four adapted global scales from the Motivational Interviewing Treatment Integrity coding manual and an overall-quality item; three newer LLMs independently rated the same transcripts in three iterations. In this fixed stimulus set, SMDP-condition dialogues received higher expert ratings for cultivating change talk, partnership, empathy, and overall quality than GPT-minimal dialogues; the two
arXiv:2504.09662v4 Announce Type: replace-cross Abstract: Multi-agent large language model simulations have the potential to model complex human behaviors and interactions. If the mechanics are set up properly, unanticipated and valuable social dynamics can surface. However, it is challenging to consistently enforce simulation mechanics while still allowing for rich and emergent dynamics. We present AgentDynEx, an AI system that helps set up, track, and repair simulations. Specifically, AgentDynEx introduces milestones that act as checkpoints and failure conditions that act as guardrails to ensure dynamics are relevant and mechanics are respected as the simulation progresses. It also introduces a method called nudging, where the system dynamically reflects on simulation progress and gently intervenes if it begins to deviate from intended outcomes. A technical evaluation found that nudging enables simulations to progress further without reducing the presence notable dynamics compared to
arXiv:2410.20696v3 Announce Type: replace-cross Abstract: Case studies have shown that software disasters snowball from technical issues to catastrophes through humans covering up problems rather than addressing them and empirical research has found the psychological safety of software engineers to discuss and address problems to be foundational to improving project success. However, the failure to do so can be attributed to psychological factors like loss aversion. We conduct a large-scale study of the experiences of 600 software engineers in the UK and USA on project success experiences. Empirical evaluation finds that approaches like ensuring clear requirements before the start of development, when loss aversion is at its lowest, correlated to 97% higher project success. The freedom of software engineers to discuss and address problems correlates with 87% higher success rates. The findings support the development of software development methodologies with a greater focus on human fa
arXiv:2202.14019v3 Announce Type: replace-cross Abstract: Maintaining proper form while exercising is important for preventing injuries and maximizing muscle mass gains. Detecting errors in workout form naturally requires estimating human's body pose. However, off-the-shelf pose estimators struggle to perform well on the videos recorded in gym scenarios due to factors such as camera angles, occlusion from gym equipment, illumination, and clothing. To aggravate the problem, the errors to be detected in the workouts are very subtle. To that end, we propose to learn exercise-oriented image and video representations from unlabeled samples such that a small dataset annotated by experts suffices for supervised error detection. In particular, our domain knowledge-informed self-supervised approaches (pose contrastive learning and motion disentangling) exploit the harmonic motion of the exercise actions, and capitalize on the large variances in camera angles, clothes, and illumination to learn
arXiv:2606.22484v2 Announce Type: replace Abstract: The adoption of agentic AI coding systems -- where autonomous agents generate, review, test, and deploy code with minimal human intervention -- creates a governance challenge in regulated industries. Existing frameworks address AI-assisted development maturity or the productivity-reliability tension but offer no mechanism for calibrating human oversight intensity to regulatory impact. We present the Governed AI-Assisted Engineering (GAIE) framework, a three-tier graduated human oversight model for agentic code generation in regulated domains. GAIE introduces the Oversight Classification Model (OCM), a deterministic decision function that classifies code generation tasks by regulatory impact, customer proximity, reversibility, and data sensitivity to route them through one of three oversight tiers: human-in-the-loop (strategic functions), human-over-the-loop (customer-impacting), or automated-with-monitoring (internal). Each tier defin
arXiv:2605.15932v2 Announce Type: replace Abstract: Designing safe and sustainable chemicals is critical to combat chemical pollution in our environment. Computational and AI-assisted methods have been developed to aid de novo molecule design. However, data on the environmental impacts of chemical compounds are sparse, resulting in low-fidelity machine learning (ML) oracles and unreliable candidate proposals. Furthermore, many automated molecular design approaches rely on numerical scoring functions that cannot fully capture the nuanced chemical intuition of expert scientists required for real-world molecular design. Instead, we present GEMS - an interactive visual analytics tool for human-in-the-loop molecular optimization that lets domain experts directly collaborate with an evolutionary genetic algorithm. Users continuously guide the search using domain knowledge through high-level, parametric modification of the scoring function alongside direct, granular control over molecule popu
arXiv:2605.12613v3 Announce Type: replace Abstract: WhatsApp is one of the most widely used messaging platforms globally, with billions of users sharing information in private groups. Yet, it offers little infrastructure to support moderation and group governance. In the absence of platform-level oversight, group admins bear the responsibility of governing group behavior. In this paper, we explore how WhatsApp group admins collaborate with AI tools to create, enforce, and maintain group rules. Drawing on a two-phase speculative design study with 20 admins in India, we examine how participants interacted with an AI assistant (Meta AI) to co-create rules and responded to a series of probes illustrating AI-assisted moderation features. Our findings show that while admins appreciated the AI's ability to surface overlooked rules and reduce their moderation burden, they were highly sensitive to issues of relational trust, data privacy, tone, and social context. We identify how group type and
arXiv:2603.28944v2 Announce Type: replace Abstract: Artificial intelligence (AI) predictions are increasingly used to inform human decisions. Here, using a behavioral implementation of the classic Newcomb's paradox in 1,305 participants, we show that AI predictions can also shape the reasoning people use to make a decision. In this paradigm, perceived predictive authority can alter how people reason about their future actions, leading them to forgo a guaranteed reward. Over 40% of participants treated AI as such a predictive authority about their own behavior, significantly increasing the odds of forgoing the guaranteed reward by a factor of 3.39 (95% CI: 2.45-4.70) and reducing earnings by 10.7-42.9%. The effect appeared across AI presentations and decision contexts and remained detectable even when predictions repeatedly failed. When people perceive AI as capable of predicting their personal behavior, the mere presence of AI predictions may shape their decision-making, narrowing the
arXiv:2601.20749v2 Announce Type: replace Abstract: How do students develop AI literacy through everyday practice rather than formal instruction? While normative AI literacy frameworks proliferate, empirical understanding of how students actually learn to work with generative AI remains limited. This study analyzes 10,536 ChatGPT messages from 36 undergraduates over one academic year, revealing five use genres -- academic workhorse, emotional companion, metacognitive partner, repair and negotiation, and trust calibration -- that constitute distinct configurations of student-AI learning. Drawing on domestication theory and emerging frameworks for AI literacy, we demonstrate that functional AI competence emerges through ongoing relational negotiation rather than one-time adoption. Students develop sophisticated genre portfolios, strategically matching interaction patterns to learning needs while exercising critical judgment about AI limitations. Notably, repair work during AI breakdowns
arXiv:2601.11049v2 Announce Type: replace Abstract: We examine whether large language models (LLMs) can predict biased decision-making in conversational settings, and whether their predictions capture not only human cognitive biases but also how those effects change under cognitive load. In a pre-registered study (N = 1,648), participants completed six classic decision-making tasks via a chatbot with dialogues of varying complexity. Participants exhibited two well-documented cognitive biases: the Framing Effect and the Status Quo Bias. Increased dialogue complexity resulted in participants reporting higher mental demand. This increase in cognitive load selectively, but significantly, increased the effect of the biases, demonstrating the load-bias interaction. We then evaluated whether LLMs (GPT-4, GPT-5, and open-source models) could predict individual decisions given demographic information and prior dialogue. While results were mixed across choice problems, LLM predictions that incor
arXiv:2512.09802v4 Announce Type: replace Abstract: This paper presents the initial stages of a design study aimed at developing a dashboard to visualize gameplay data of the Commander format from Magic: The Gathering. We conducted a user-task analysis to identify requirements for a data visualization dashboard tailored to the Commander format. Afterward, we proposed a design for the dashboard, leveraging visualizations to address players' needs and pain points for typical data analysis tasks in the context domain. Then, we followed-up with a structured user test to evaluate players' comprehension and preferences of data visualizations. Results show that players prioritize contextually relevant, outcome-driven metrics over peripheral ones, and that canonical charts like heatmaps and line charts support higher comprehension than complex ones such as scatterplots or icicle plots. Our findings also highlight the importance of localized views, user customization, and progressive disclosure
arXiv:2509.13742v4 Announce Type: replace Abstract: Science communication revision requires writers to dynamically balance scientific exposition and narrative engagement - a process where writers often struggle with competing directions. Existing LLM-assisted tools help with co-writing, but offer limited support for navigating this iterative, multi-directional revision process. To address this gap, we designed Spatial Balancing, an exploratory revision environment that maps rhetorical goals and revision strategies onto a two-dimensional spatial canvas for experienced science communication creators with domain expertise but lacking formal professional training. By building a design space of communication strategies and embedding them into a spatial exploratory canvas, our system treats feedback as navigational cues rather than prescriptive judgments. Our findings show that this integrated revision environment helps writers stay focused on writing goals, reason about revision as trajecto
arXiv:2508.08242v2 Announce Type: replace Abstract: Group decision-making often suffers from uneven information sharing, hindering decision quality. While large language models (LLMs) have been widely studied as aids for individuals, their potential to support groups of users, potentially as facilitators, is relatively underexplored. We present a pre-registered randomized experiment with 1,475 participants assigned to 281 live groups completing a hidden profile task--selecting an optimal city for a hypothetical sporting event--under one of four facilitation conditions: no facilitation, a one-time message prompting information sharing, a human facilitator, or an LLM (GPT-4o) facilitator. We find that LLM facilitation increased information shared within a discussion by raising the minimum level of engagement with the task among group members, and that these gains came at limited cost in terms of participants' attitudes towards the task, their group, or their facilitator. Whether by human
arXiv:2507.12721v3 Announce Type: replace Abstract: Human-AI interfaces play a pivotal role in integrating clinicians' expertise with artificial intelligence to enhance both healthcare practice and research. However, designing effective interfaces in this domain remains a significant challenge. The inherent complexity of medical data, the influence of domain-specific conventions, and the diverse needs of clinical users compound the challenge of developing practical and usable solutions. In this study, we review existing solutions and synthesize a set of design patterns - recurring approaches that support the design of human-AI interfaces in clinical settings. We conducted a comprehensive literature review of human-AI interaction designs in clinical contexts, through which we identified 15 information entities commonly presented to users and 12 design patterns used to organize and communicate this information effectively. For each design pattern, we summarize the underlying design probl
arXiv:2507.03670v2 Announce Type: replace Abstract: Writing longer prompts for an AI assistant to generate a story increases psychological ownership, a user's feeling that the writing belongs to them. To encourage users to write longer prompts, we evaluated two interaction techniques that modify the prompt entry interface of chat-based generative AI assistants: pressing and holding the prompt submission button, and continuously moving a slider up and down when submitting a short prompt. A within-subjects experiment investigated the effects of such techniques on prompt length and psychological ownership, and results showed that these techniques increased prompt length and led to higher psychological ownership than baseline techniques. A second experiment further augmented these techniques by showing AI-generated suggestions for how the prompts could be expanded. This further increased prompt length, but did not lead to improvements in psychological ownership. Our results show that simpl
arXiv:2504.17331v3 Announce Type: replace Abstract: Locomotion plays a crucial role in shaping the user experience within virtual reality environments. In particular, hands-free locomotion offers a valuable alternative by supporting accessibility and freeing users from reliance on handheld controllers. To this end, traditional speech-based methods often depend on rigid command sets, limiting the naturalness and flexibility of interaction. In this study, we propose a novel locomotion technique powered by large language models (LLMs), which allows users to navigate virtual environments using natural language with contextual awareness. We evaluate three locomotion methods: controller-based teleportation, voice-based steering, and our language model-driven approach. Our evaluation combines eye-tracking data analysis, including exploratory explainable machine learning analysis with SHAP, and standardized questionnaires (SUS, IPQ, CSQ-VR, NASA-TLX) to examine user experience through both obj
arXiv:2503.20666v2 Announce Type: replace Abstract: Thematic analysis (TA) is a widely used qualitative approach for uncovering latent meanings in unstructured text data. TA provides valuable insights in healthcare but is resource-intensive. Large Language Models (LLMs) have been introduced to perform TA, yet their applications in high-stakes healthcare settings, particularly for qualitative clinical interview analysis, remain limited. Here, we propose TAMA: A Human-AI Collaborative Thematic Analysis framework using Multi-Agent LLMs for clinical interviews. We leverage the scalability and coherence of multi-agent systems through structured conversations between agents and coordinate the expertise of cardiac experts in TA. Using interview transcripts from parents of children with Anomalous Aortic Origin of a Coronary Artery (AAOCA), a rare congenital heart disease, we demonstrate that TAMA outperforms single-agent LLM TA approaches, achieving higher thematic hit rate, coverage, and dist
arXiv:2411.11449v3 Announce Type: replace Abstract: Deploying AI systems in public institutions can have far-reaching consequences for many people, making it a matter of public interest. Providing opportunities for stakeholders to come together, understand these systems, and debate their merits and harms is thus essential. Explainable AI often focuses on individuals, but deliberation benefits from group settings, which are underexplored. To address this gap, we present findings from an interview study with 8 focus groups and 12 individuals. Our findings provide insight into how explanations support AI novices in deliberating alone and in groups. Participants used modular explanations with four information categories to solve tasks and decide about an AI system's deployment. We found that the explanations supported groups in creating shared understanding and in finding arguments for and against the system's deployment. In comparison, individual participants engaged with explanations in
arXiv:2607.04860v1 Announce Type: cross Abstract: Gaze target estimation, the task of predicting where a person is looking in a scene, is crucial to understanding human attention and intent. It is a challenging task that combines high-level understanding of global scene semantics and precise spatial reasoning using human appearance (e.g. pose, eye orientation). As a result, human-level performance remains elusive for existing models, limiting their practical application. To this end, we propose PaGE (Practical Gaze Estimator), a gaze estimation model that explicitly models the complex interaction between scene and head features. Using a PaGE model with a large ViT-H+ backbone as the teacher, we further distill student models with lighter backbones on a much larger and more diverse unlabeled dataset. The architectural improvements and novel training recipe allow PaGE to achieve state-of-the-art performance on several gaze estimation tasks, outperforming humans in 7 out of 9 metrics whil
arXiv:2607.04438v1 Announce Type: cross Abstract: Research dissemination, turning a paper into a poster, a talk video, and a blog post, is still a manual last mile. Prior automation treats each artifact in isolation that each re-extract the paper from scratch, usually ship one-way renders the author cannot reopen in PowerPoint or Word, and gates quality on soft VLM-preference scores that plateau while load-bearing sections still read as empty. We argue this last mile is best built as a composition of skills: thin agent-readable contracts that share one upstream extractor and wrap deterministic primitives in a measured-fill loop whose exits are hard pass/fail render gates. We instantiate this as ResearchStudio-Reel, five Claude Code and Codex skills organized into one shared extractor (Paper2Assets), three editable generators (Paper2Poster, Paper2Video, Paper2Blog), and one interactive convergence layer (Paper2Reel). Paper2Assets extracts each paper once into a shared bundle that can be
arXiv:2607.04025v1 Announce Type: cross Abstract: Traditional Chinese medicine (TCM) prescription support requires patient-specific reasoning from clinical narratives to syndromes, treatment principles, herbs, and doses. Direct language-model generation can produce fluent prescriptions, but its decisions are difficult to audit against explicit clinical evidence. Static TCM knowledge resources provide useful priors, but they cannot determine which diagnostic and prescription relations should be emphasized for an individual patient. We propose a patient-conditioned dual hypergraph framework for auditable TCM prescription support. The first hypergraph organizes symptom, tongue, pulse, and other clinical evidence around syndrome and treatment-principle reasoning. The second hypergraph organizes syndrome, treatment, disease-context, herb, retrieval, and dose-prior evidence for prescription construction. Unlike static knowledge graphs or fixed hypergraphs, both hypergraphs are dynamically we
arXiv:2607.03844v1 Announce Type: cross Abstract: Imagined speech decoding using EEG signals has emerged as a promising frontier in brain-computer interface (BCI) research, particularly to restore communication for individuals with severe speech impairments. However, decoding imagined speech remains a complex task due to the non-stationary, low-amplitude, and highly variable nature of EEG signals. Existing methods often rely on classical machine learning or deep learning models that fail to exploit spike-based temporal dynamics or event-driven firing mechanisms of biological neurons, which are naturally modeled by spiking neural networks (SNNs). In this study, we propose a hybrid decoding pipeline that extracts temporal representations using convolutional neural networks (CNNs) followed by biologically inspired temporal classification via SNNs. To our knowledge, this is the first study to integrate SNNs into EEG-based imagined speech decoding. Experimental results show that the propose